Convergence of Discrete-Time Recurrent Neural Networks with Variable Delay

In this paper, some global exponential stability criteria for the equilibrium point of discrete-time recurrent neural networks with variable delay are presented by using the linear matrix inequality (LMI) approach. The neural networks considered are assumed to have asymmetric weighting matrices throughout this paper. On the other hand, by applying matrix decomposition, the model is embedded into a cooperative one, the latter possesses important order-preserving properties which are basic to our analysis. A sufficient condition is obtained ensuring the componentwise exponential stability of the system with specific performances such as decay rate and trajectory bounds.

[1]  M. Forti,et al.  Global convergence of neural networks with discontinuous neuron activations , 2003 .

[2]  Shun-ichi Amari,et al.  Global Convergence Rate of Recurrently Connected Neural Networks , 2002, Neural Computation.

[3]  Jinde Cao.  A set of stability criteria for delayed cellular neural networks , 2001 .

[4]  K. Gopalsamy,et al.  Stability of artificial neural networks with impulses , 2004, Appl. Math. Comput..

[5]  Jinde Cao,et al.  Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays , 2004, Neural Networks.

[6]  Jinde Cao,et al.  Global exponential stability and periodic solutions of recurrent neural networks with delays , 2002 .

[7]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[8]  R. Westervelt,et al.  Stability of analog neural networks with delay. , 1989, Physical review. A, General physics.

[9]  K. Gopalsamy,et al.  Exponential stability of continuous-time and discrete-time cellular neural networks with delays , 2003, Appl. Math. Comput..

[10]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Jinde Cao.  Global stability conditions for delayed CNNs , 2001 .

[12]  K. Gopalsamy,et al.  Stability in asymmetric Hopfield nets with transmission delays , 1994 .

[13]  Tianping Chen,et al.  Global Convergence of Delayed Neural Network Systems , 2003, Int. J. Neural Syst..

[14]  Marco Gilli,et al.  Stability of cellular neural networks and delayed cellular neural networks with nonpositive templates and nonmonotonic output functions , 1994 .

[15]  Xingfu Zou,et al.  Stabilization role of inhibitory self-connections in a delayed neural network , 2001 .

[16]  Jinde Cao,et al.  Estimation of the Domain of Attraction and the Convergence Rate of a Hopfield Associative Memory and an Application , 2000, J. Comput. Syst. Sci..

[17]  T. Chu,et al.  A decomposition approach to analysis of competitive–cooperative neural networks with delay , 2003 .

[18]  K. Gopalsamy,et al.  Dynamics of a class of discete-time neural networks and their comtinuous-time counterparts , 2000 .

[19]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[20]  Jin Xu,et al.  On the global stability of delayed neural networks , 2003, IEEE Trans. Autom. Control..

[21]  Jinde Cao,et al.  An estimation of upperbound of delays for global asymptotic stability of delayed Hopfield neural networks , 2002 .

[22]  Jinde Cao,et al.  Global asymptotic stability of a general class of recurrent neural networks with time-varying delays , 2003 .

[23]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[24]  Jinde Cao,et al.  On stability of delayed cellular neural networks , 1999 .

[25]  Jun Wang,et al.  Global stability of a class of discrete-time recurrent neural networks , 2002 .

[26]  Xuesong Jin,et al.  Global stability analysis in delayed Hopfield neural network models , 2000, Neural Networks.

[27]  G. Altarelli,et al.  Inclusive beauty decays and the spectator model , 1991 .

[28]  E. Sánchez,et al.  Input-to-state stability (ISS) analysis for dynamic neural networks , 1999 .

[29]  A. Michel,et al.  Asymptotic stability of discrete-time systems with saturation nonlinearities with applications to digital filters , 1992 .

[30]  Liang Jin,et al.  Globally asymptotical stability of discrete-time analog neural networks , 1996, IEEE Trans. Neural Networks.

[31]  Xiaofeng Liao,et al.  (Corr. to) Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach , 2002, Neural Networks.

[32]  S. Arik.  Global robust stability of delayed neural networks , 2003 .

[33]  Qidi Wu,et al.  Impulsive control for the stabilization and synchronization of Lorenz systems , 2002 .

[34]  Vedat Tavsanoglu,et al.  A new parameter range for the stability of opposite-sign cellular neural networks , 1993 .

[35]  Frank L. Lewis,et al.  Multilayer discrete-time neural-net controller with guaranteed performance , 1996, IEEE Trans. Neural Networks.

[36]  Jinde Cao,et al.  Global exponential stability of reaction–diffusion recurrent neural networks with time-varying delays , 2003 .

[37]  Jinde Cao,et al.  Novel Stability Criteria for Delayed Cellular Neural Networks , 2003, Int. J. Neural Syst..

[38]  Leon O. Chua,et al.  Stability of a class of nonreciprocal cellular neural networks , 1990 .

[39]  Shun-ichi Amari,et al.  Stability of asymmetric Hopfield networks , 2001, IEEE Trans. Neural Networks.

[40]  Jitao Sun,et al.  Impulsive control of a nuclear spin generator , 2003 .

[41]  Chien-Yu Lu,et al.  Stability of cellular neural networks with time-varying delay , 2003 .